Metric Learning For Person Re-identification Research Articles

Datum-Adaptive Local Metric Learning for Person Re-identification

Person re-identification (PRID) is a challenging problem in multi-camera surveillance systems. In this paper, we propose a novel Datum-Adaptive Local Metric learning method for PRID, which learns individual local feature projection for each image sample according to the current data distribution and projects all samples into a common discriminative space for similarity measure. We adopt an approximate strategy based on Local Coordinate Coding to learn local projections. Anchor points are first generated by clustering and the local projection of each sample is then approximated by the linear combination of a set of projection bases, which are associated with the anchor points. Experimental results demonstrate that the proposed approach obtains superior performance compared with state-of-the-art methods on public benchmarks.

Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities.

Person re-identification aims to match people across non-overlapping camera views, which is an important but challenging task in video surveillance. In order to obtain a robust metric for matching, metric learning has been introduced recently. Most existing works focus on seeking a Mahalanobis distance by employing sparse pairwise constraints, which utilize image pairs with the same person identity as positive samples, and select a small portion of those with different identities as negative samples. However, this training strategy has abandoned a large amount of discriminative information, and ignored the relative similarities. In this paper, we propose a novel relevance metric learning method with listwise constraints (RMLLCs) by adopting listwise similarities, which consist of the similarity list of each image with respect to all remaining images. By virtue of listwise similarities, RMLLC could capture all pairwise similarities, and consequently learn a more discriminative metric by enforcing the metric to conserve predefined similarity lists in a low-dimensional projection subspace. Despite the performance enhancement, RMLLC using predefined similarity lists fails to capture the relative relevance information, which is often unavailable in practice. To address this problem, we further introduce a rectification term to automatically exploit the relative similarities, and develop an efficient alternating iterative algorithm to jointly learn the optimal metric and the rectification term. Extensive experiments on four publicly available benchmarking data sets are carried out and demonstrate that the proposed method is significantly superior to the state-of-the-art approaches. The results also show that the introduction of the rectification term could further boost the performance of RMLLC.

Regularized local metric learning for person re-identification

In this paper, we propose a regularized local metric learning (RLML) method for person re-identification. Unlike existing metric learning based person re-identification methods which learn a single distance metric to measure the similarity of each pair of human body images, our method combines global and local metrics to represent the within-class and between-class variances. By doing so, we utilize the local distribution of the training data to avoid the overfitting problem. In addition, to address the lacking of training samples in most person re-identification systems, our method also regulates the covariance matrices in a parametric manner, so that discriminative information can be better exploited. Experimental results on four widely used datasets demonstrate the advantage of our proposed RLML over both existing metric learning and state-of-the-art person re-identification methods.